© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 31-GEMMASCOPE-RES-131K
    6. 21285
    Prev
    Next
    INDEX
    Explanations

    references to familial relationships and personal connections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    died or survived

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     OMITBAD
    -0.47
    ValueGenerated
    -0.44
    hicles
    -0.39
     interacting
    -0.37
    anyway
    -0.37
    ことにしました
    -0.37
    jspb
    -0.37
    LookAnd
    -0.36
    exels
    -0.36
    vacy
    -0.36
    POSITIVE LOGITS
     predeceased
    0.96
     survives
    0.92
     preceded
    0.82
     précé
    0.73
     precedes
    0.73
     survive
    0.70
     precede
    0.69
     sobrevi
    0.68
    survi
    0.65
     SURV
    0.64
    Activations Density 0.008%

    No Known Activations